Wheel tread derailment detection method and system for railway vehicle

Abstract

The invention provides a wheel tread derailment detection method and system for a railway vehicle. According to the method, jacking driving devices with jacking rotating wheels are symmetrically arranged on the two longitudinal sides of a track, a pressure sensing unit is arranged between the two jacking rotating wheels, optical detection units with orthogonal optical paths are installed on the outer sides, and displacement measurement units are integrated on the jacking rotating wheels, so that a three-dimensional detection network is formed. During detection, a top rotating wheel lifts a wheel step by step, a blocking signal, tread pressure and a vertical displacement parameter are synchronously collected, and a space mapping relation between a pressure decreasing path and a displacement abnormal point is established; converting the blocking signal into a blocking release rate, and calculating a displacement accumulated value in combination with a space mapping relation; and when the displacement accumulated value is continuously increased and the blocking release rate exceeds a threshold value, wheel-rail separation is judged, and jacking is controlled to be stopped. Through cooperative detection and analysis of multiple sensors, accurate judgment and self-adaptive jacking control of the wheel-rail separation state are achieved, and the problem of wheel diameter adaptability of a traditional fixed jacking mode is effectively solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for detecting wheel tread derailment of a rail vehicle. Background Art

[0002] The wheels of rail vehicles are subjected to alternating stresses during long-term operation, which can easily lead to fatigue defects and directly affect driving safety. To ensure safety, the wheels must be regularly inspected with ultrasonic flaw detection. Due to the high cost and low efficiency of wheel disassembly and assembly, online flaw detection equipment is currently widely used, that is, the inspection is completed while the wheels remain installed. However, there are differences in wheel diameters (such as the deviation between the minimum wheel diameter and the standard wheel diameter caused by wear), which places precise control requirements on the lifting mechanism of the flaw detection equipment: it is necessary to ensure that wheels of different wheel diameters can reliably detach from the rails, while avoiding excessive lifting that affects the inspection process.

[0003] Existing online ultrasonic flaw detection equipment typically uses a wheel-lifting mechanism. This mechanism works as follows: a lifting mechanism lifts the wheel to a fixed height, clearing it from the rail. The wheel is then rotated, allowing the ultrasonic probe to contact the wheel surface for inspection. However, existing solutions rely on a preset fixed lifting distance and fail to account for the impact of varying wheel diameters. Summary of the Invention

[0004] The present application provides a method and system for detecting wheel tread derailment of a rail vehicle, which are used to solve the problem of poor derailment detection effect caused by the fixed jacking method in the prior art.

[0005] In a first aspect, the present application provides a method for detecting wheel tread derailment of a rail vehicle, wherein lifting drive devices are symmetrically arranged on both sides of the longitudinal track, each lifting drive device includes two lifting wheels, which are used to lift the wheel. A pressure sensing unit is arranged between the two lifting wheels. An optical detection unit is installed on the outer side of the lifting drive device, and its optical path direction is orthogonal to the wheel motion plane. At the same time, a displacement measurement unit is integrated on the lifting wheel. When the lifting wheel lifts the wheel, the displacement measurement unit moves synchronously to generate a vertical displacement parameter of the wheel. The pressure sensing unit, the optical detection unit, and the displacement measurement unit form a three-dimensional detection coverage area in the wheel-rail contact area. When the wheel contacts the track, the optical path of the optical detection unit is completely blocked by the wheel.

[0006] The method comprises:

[0007] During the process of the jacking drive device's jacking wheel gradually raising the wheel, a blocking signal state of the optical detection unit, a tread pressure change parameter output by the pressure sensing unit, and a vertical displacement parameter generated by the displacement measurement unit are obtained to establish a spatial mapping relationship between an expansion path of a pressure decreasing region and a distribution characteristic of abnormal displacement points;

[0008] Mapping the blocking signal state to a blocking release rate of the optical detection channel, and calculating the cumulative displacement value when the wheel tread is separated based on the spatial mapping relationship and the blocking release rate of the optical detection channel;

[0009] When the accumulated displacement value presents a unidirectional increasing characteristic in the continuous lifting stage and the blocking release rate of the optical detection channel is greater than a preset threshold, the wheel-rail separation is determined, and a control instruction is generated to control the jacking drive device to terminate the operation.

[0010] Optionally, it also includes:

[0011] During the lifting process, images of the contact surfaces of the wheel and the rail are synchronously collected, and illumination reflection characteristics and contour deformation parameters of the contact area are extracted from the contact surface images;

[0012] Comparing the illumination reflection characteristics with a preset standard reflection template in a wheel-rail fitting state to generate a deformation compensation factor;

[0013] The displacement accumulation value is dynamically corrected based on the deformation compensation factor, and the boundary accuracy of the spatial mapping relationship is optimized by fusing the contour deformation parameter.

[0014] Optionally, acquiring the blocking signal state of the optical detection unit, the tread pressure change parameter output by the pressure sensing unit, and the vertical displacement parameter generated by the displacement measurement unit to establish a spatial mapping relationship between the pressure decrease area expansion path and the displacement abnormal point distribution characteristics includes:

[0015] Calculating the change rate of the blocking release rate corresponding to the optical detection channel according to the blocking signal state of the optical detection unit, and extracting the peak coordinate information corresponding to the change rate;

[0016] Extracting the expansion direction and decreasing gradient of the pressure decreasing area from the tread pressure change parameter output by the pressure sensing unit to determine the pressure decreasing starting point and the pressure decreasing propagation path;

[0017] identifying a spatial distribution of displacement anomalies in the vertical displacement parameters generated by the displacement measurement unit;

[0018] Based on the peak coordinate information, the pressure decrease starting point and pressure decrease propagation path, and the spatial distribution of the displacement abnormal points, a spatial mapping relationship between the pressure decrease area expansion path and the displacement abnormal point distribution characteristics is established.

[0019] Optionally, establishing a spatial mapping relationship between the pressure decrease area expansion path and the distribution characteristics of the displacement abnormal points based on the peak coordinate information, the pressure decrease starting point and the pressure decrease propagation path, and the spatial distribution of the displacement abnormal points includes:

[0020] Matching the time point in the peak coordinate information with the occurrence time of the pressure decrease starting point, and if the time difference between the two is less than a set tolerance, marking the pressure decrease starting point as a valid trigger point;

[0021] Taking the effective trigger point as the starting point, multiple directional associated areas are delineated in the wheel-rail contact area according to the extension direction of the pressure decrease propagation path, and the spatial distribution of displacement abnormal points in each directional associated area is counted;

[0022] Proportionally distribute the spatial distribution of the displacement anomaly points and the pressure decrease gradient of the corresponding directional association area. If the ratio of density to gradient in any directional association area exceeds a dynamic threshold, the directional association area is determined to be the spatial mapping area of the pressure decrease expansion path and the displacement anomaly points.

[0023] The coverage and connection relationship of all spatial mapping areas are used as the spatial mapping relationship between the expansion path of the pressure reduction area and the distribution characteristics of the displacement anomaly points.

[0024] Optionally, mapping the blocking signal state to a blocking release rate of an optical detection channel, and calculating the cumulative displacement value when the wheel tread is separated according to the spatial mapping relationship and in combination with the blocking release rate of the optical detection channel, includes:

[0025] Counting the duration of the blocking signal of each optical detection channel during the lifting process, and calculating the blocking release weight factor of each optical detection channel according to the blocking signal duration;

[0026] The ratio of the number of optical detection channels where the blocking signals disappear to the total number of optical detection channels is converted into a blocking release rate sequence according to the lifting time sequence;

[0027] Screening out a wheel tread area that coincides with a distribution area of abnormal displacement points according to a pressure decreasing expansion path marked in the spatial mapping relationship;

[0028] The vertical displacement increments detected by all displacement measurement units in the wheel tread area during the lifting phase are accumulated, and each vertical displacement increment is weightedly corrected according to the blocking release rate sequence and the corresponding blocking release weight factor to generate a displacement accumulation value.

[0029] Optionally, calculating the change rate of the blocking release rate corresponding to the optical detection channel according to the blocking signal state of the optical detection unit, and extracting peak coordinate information corresponding to the change rate includes:

[0030] Divide the blocking release rate sequence by the preset time window, calculate the difference of the blocking release rate in each time window, and divide the difference by the time window duration to obtain the change rate sequence;

[0031] The change rate sequence is traversed to identify the local maximum point whose rate value is greater than the rate value of the adjacent time windows, and the corresponding timestamp and the associated optical detection channel position number are recorded to form peak coordinate information.

[0032] Optionally, extracting the expansion direction and decreasing gradient of the pressure decreasing area in the tread pressure change parameter output by the pressure sensing unit to determine the pressure decreasing starting point and the pressure decreasing propagation path includes:

[0033] The wheel tread is divided into grid units, and the decrease amplitude of the pressure change parameter in each grid unit is counted;

[0034] The grid cell with the largest pressure drop is taken as the starting point of pressure drop, and starting from the pressure drop starting point, the path is traced along the direction of increasing pressure drop of adjacent grid cells until a pressure increase or stable area is detected, thereby forming a pressure drop propagation path;

[0035] The decreasing gradient of the pressure decreasing propagation path is calculated according to the ratio of the pressure drop amplitude of each grid unit on the pressure decreasing propagation path to the path length.

[0036] Optionally, identifying the spatial distribution of abnormal displacement points in the vertical displacement parameters generated by the displacement measurement unit includes:

[0037] Continuously sampling the vertical displacement parameter generated by the displacement measurement unit, detecting the displacement increment difference between adjacent sampling points, and marking the time period between the adjacent sampling points as a nonlinear change section if the displacement increment difference exceeds a set mutation threshold;

[0038] Record the starting timestamps of all nonlinear change segments and calculate the maximum time difference between the starting timestamps detected by different displacement measurement units as the timing deviation;

[0039] The nonlinear change segments are grouped according to the timing deviation, and nonlinear change segment groups whose time differences are less than the synchronization threshold are screened out. In each nonlinear change segment group, displacement points with unidirectional sudden increases are screened out based on the directional consistency of the displacement increments. These points are marked as displacement anomalies and the position coordinates corresponding to the displacement anomalies are recorded.

[0040] The spatial distribution of the displacement anomaly points is determined according to the position coordinates corresponding to the multiple displacement anomaly points.

[0041] Optionally, when the accumulated displacement value presents a unidirectional increasing characteristic during the continuous lifting stage and the blocking release rate of the optical detection channel is greater than a preset threshold, wheel-rail separation is determined, and a control instruction is generated to control the jacking drive device to terminate the operation, including:

[0042] Record the cumulative displacement values in the order of the lifting stages. If the cumulative displacement value of the current stage is greater than that of the previous stage and the difference between the cumulative displacement values continues to increase, it is marked as unidirectional increase;

[0043] Counting the proportion of channels in the optical detection channels whose blocking release rate is greater than a preset threshold, if the proportion of the number of channels exceeds the preset threshold in a consecutive number of lifting stages, it is marked as meeting the effective ratio standard;

[0044] When the one-way increasing mark and the effective ratio reaching mark exist at the same time, a control instruction is generated to control the lifting drive device to terminate the operation;

[0045] The method further comprises:

[0046] In response to the control instruction, the driving rotation unit is started to drive the wheel to rotate, and the acoustic wave detection unit is regulated to perform defect detection operations in accordance with the wheel surface based on the channel activation sequence of the optical detection unit.

[0047] In a second aspect, the present application provides a wheel tread derailment detection system for a rail vehicle, comprising a lifting drive device, an optical measurement unit, and a processing unit; wherein each lifting drive device comprises two lifting wheels, a pressure sensing unit, and a displacement detection unit, and the lifting drive devices are arranged on both sides of the longitudinal direction of the track, and each lifting drive device comprises two lifting wheels, and the lifting wheels are used to lift the wheels;

[0048] A pressure sensing unit is provided between the two top rotating wheels, and the pressure sensing unit is used to output tread pressure change parameters;

[0049] An optical detection unit is installed on the outer side of the jacking drive device, and its light path direction is orthogonal to the wheel movement plane. When the wheel contacts the track, the light path of the optical detection unit is completely blocked by the wheel;

[0050] The top runner is integrated with a displacement measuring unit. When the top runner lifts the wheel, the displacement measuring unit moves synchronously to generate the vertical displacement parameters of the wheel. The pressure sensing unit, the optical detection unit and the displacement measuring unit form a three-dimensional detection coverage area in the wheel-rail contact area.

[0051] The processing unit is used to obtain the blocking signal state of the optical detection unit, the tread pressure change parameter output by the pressure sensing unit, and the vertical displacement parameter generated by the displacement measurement unit during the process of the jacking drive device raising the wheel step by step, so as to establish a spatial mapping relationship between the pressure decrease area expansion path and the displacement abnormality point distribution characteristics; map the blocking signal state to the blocking release rate of the optical detection channel, and calculate the displacement accumulation value when the wheel tread is separated according to the spatial mapping relationship and the blocking release rate of the optical detection channel; when the displacement accumulation value presents a unidirectional increasing characteristic in the continuous lifting stage and the blocking release rate of the optical detection channel is greater than a preset threshold, it is determined that the wheel and rail are separated, and a control instruction is generated to control the jacking drive device to terminate the operation.

[0052] In the technical solution of the present application, a three-dimensional detection network is formed in the wheel-rail contact area by means of a pressure sensing unit, an optical detection unit and a displacement measurement unit, and blocking signals, tread pressure change parameters and vertical displacement parameters are collected in real time to realize collaborative perception of multi-dimensional data and improve the comprehensiveness and reliability of detection. Based on the correlation analysis of the expansion path of the pressure decrease area and the distribution characteristics of the displacement anomaly points, the physical propagation characteristics of the wheel-rail separation process are accurately modeled to provide high-confidence data support for the judgment. The blocking signal state is mapped to the blocking release rate, and the displacement accumulation value is corrected in combination with the spatial mapping relationship to eliminate noise interference and truly reflect the effective separation amount of the wheel lifting. Through the dual verification of the unidirectional increasing characteristics of the displacement accumulation value and the blocking release rate threshold, the absolute reliability of the wheel-rail separation judgment is ensured to avoid misjudgment and equipment damage.

[0053] Furthermore, the technical solution of this application also synchronously captures images of the wheel-rail contact surface during the lifting process, extracts illumination reflection characteristics and contour deformation parameters, generates deformation compensation factors through differential comparison, dynamically corrects the accumulated displacement value, and optimizes the boundary accuracy of the spatial mapping relationship. Through image feature analysis and deformation compensation mechanisms, displacement detection errors caused by wheel surface deformation or foreign matter adhesion are significantly reduced. Illumination reflection difference comparison accurately locates abnormal areas, and contour parameters optimize spatial mapping boundaries, improving the system's adaptability and detection accuracy in complex working conditions.

[0054] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] Figure 1 This is an architectural diagram of a rail vehicle wheel tread derailment detection system provided in an embodiment of the present application;

[0057] Figure 2 A schematic structural diagram of a rail vehicle wheel tread derailment detection system provided in an embodiment of the present application;

[0058] Figure 3 A schematic structural diagram of another rail vehicle wheel tread derailment detection system provided in an embodiment of the present application;

[0059] Figure 4 A schematic structural diagram of another rail vehicle wheel tread derailment detection system provided in an embodiment of the present application;

[0060] Figure 5 A flowchart of a method for detecting wheel tread derailment of a rail vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0062] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0063] Research has found that existing online ultrasonic flaw detection technology for rail vehicle wheels relies on a fixed-lift wheel-turning mechanism, resulting in critical flaws in scenarios with varying wheel diameters. The smallest wheel diameter fails to fully derail due to insufficient lifting, causing damage to the wheel from friction between the tread and the rail during rotation. Meanwhile, excessive lifting of the largest wheel diameter affects probe contact accuracy, leading to distorted detection signals. This discrepancy stems from the fixed-lift strategy's indifferent handling of wheel diameter variations, necessitating a dynamic, adaptive separation and determination method.

[0064] In response to the above problems, the present invention proposes a wheel tread derailment detection method based on multi-source sensor fusion. The core of the method is to capture the changing characteristics of the wheel-rail contact state in real time through three-dimensional collaborative monitoring of the pressure sensing unit, the optical detection unit and the displacement measurement unit. Specifically, during the jacking process, by analyzing the spatial expansion characteristics of the tread pressure reduction path, the release ratio of the optical blocking signal and the cumulative trend of the vertical displacement, the critical state of wheel-rail separation is dynamically determined, and the jacking height is adaptively controlled. This method abandons the traditional fixed jacking distance mode and ensures that wheels of different wheel diameters can be reliably derailed at the minimum necessary height through the spatiotemporal correlation and fusion calculation of multi-sensor data, thereby avoiding insufficient jacking in small wheel diameter scenarios and eliminating excessive lifting in large wheel diameter scenarios. It fundamentally solves the problems of detection failure and equipment damage caused by wheel diameter differences in the existing technology, and significantly improves the safety and process consistency of flaw detection operations.

[0065] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0066] Figure 1 The present invention provides a structural diagram of a wheel tread derailment detection system for a railway vehicle, as shown in FIG. Figure 1 As shown, the system includes a lifting drive device 11, an optical measurement unit 12 and a processing unit 13; wherein each lifting drive device 11 includes two lifting wheels 11a and 11b, a pressure sensing unit 11c and a displacement detection unit 11d;

[0067] Among them, the connection relationship between the various units of the system is as follows Figure 2 As shown, in Figure 2 middle( Figure 2 Only one side of the track is shown as an example), and jacking drive devices 11 are symmetrically arranged on both sides of the track in the longitudinal direction. Each jacking drive device includes jacking wheels 11a and 11b, which are used to lift the wheels on the same side.

[0068] like Figure 3 As shown, a pressure sensing unit 11c is disposed between the two top runners 11a and 11b. This pressure sensing unit 11c can utilize a piezoelectric, strain gauge, or capacitive sensor. When the wheel is not lifted, the pressure sensing unit 11c can detect the pressure at the wheel-rail contact surface. During wheel lifting, it can detect changes in the pressure gradient at the wheel-rail contact surface and output a tread pressure change parameter. This tread pressure change parameter is then used by the subsequent processing unit 14 to determine whether the track is separated.

[0069] Optical detection units 12a and 12b are installed on the outer side of the lifting drive device 11, wherein the light path direction between the optical detection units 12a and 12b is orthogonal to the wheel motion plane. Figure 4 As shown, when the wheel contacts the track, the optical path of the optical detection unit is completely blocked by the wheel. The top runners are configured as hollow structures. When the top runners 11a and 11b lift the wheel, the optical signal emitted by optical detection unit 12a can be received by optical detection unit 12b through the hollow structure of the top runners. When optical detection unit 12b receives the optical signal, processing unit 13 determines that the optical path is not blocked by the wheel. Optical detection unit 12 employs one or a combination of through-beam, specular reflection, or diffuse reflection optical sensors. Light is emitted by optical detection unit 12, and processing unit 13 determines whether the vehicle and track are separated based on the blocked light path.

[0070] At the same time, a displacement measuring unit 11d is integrated on the top turntable. When the top turntable lifts the wheel, the displacement measuring unit 11d moves synchronously to generate the vertical displacement parameter of the wheel. The displacement measuring unit 11d measures the rotation angle of the top turntable screw through an encoder to convert the lifting height, or directly detects the hydraulic cylinder stroke through a linear potentiometer to ensure that the vertical displacement parameter is strictly synchronized with the actual lifting amount of the wheel. It should be noted that Figure 2 The installation position of the displacement measuring unit 11d shown is only an example and can be set according to specific needs. It is only necessary to integrate the displacement measuring unit 11d on the top rotating wheel.

[0071] Through the above arrangement, the pressure sensing unit 11c, the optical detection unit 12 and the displacement measurement unit 11d in the system form a three-dimensional detection coverage area in the wheel-rail contact area.

[0072] In the three-dimensional detection coverage area, the processing unit 13 is used to obtain the blocking signal state of the optical detection unit 12, the tread pressure change parameter output by the pressure sensing unit 11c, and the vertical displacement parameter generated by the displacement measurement unit 11d during the process of the jacking wheel of the jacking drive device 11 raising the wheel step by step, and establish a spatial mapping relationship between the expansion path of the pressure decreasing area and the distribution characteristics of the displacement abnormality point by fusing the expansion direction of the pressure decreasing area, the spatial distribution of the displacement abnormality point and the correlation characteristics of the optical path blocking release rate; map the blocking signal state to the blocking release rate of the optical detection channel, and calculate the cumulative displacement value when the wheel tread is separated according to the spatial mapping relationship and the blocking release rate of the optical detection channel; when the cumulative displacement value shows a unidirectional increasing characteristic in the continuous lifting stage and the blocking release rate of the optical detection channel is greater than the preset threshold, the wheel-rail separation is determined, and a control instruction is generated to control the jacking drive device 11 to terminate the operation.

[0073] Optionally, the system also includes a driving rotation unit (not shown in the figure) and an acoustic wave detection unit (not shown in the figure), wherein the driving rotation unit is used to drive the wheel to rotate after the wheel-rail is separated, and the acoustic wave detection unit dynamically adjusts the probe fitting trajectory based on the channel activation sequence of the optical detection unit.

[0074] The processing unit 13 is further configured to start the driving rotation unit to drive the wheel to rotate by responding to the control instruction, and to control the acoustic wave detection unit to perform defect detection operations.

[0075] In view of the above system, the embodiment of the present application provides a method for detecting wheel tread derailment of a railway vehicle. Figure 5 A flow chart of a method for detecting wheel tread derailment of a railway vehicle is provided in an embodiment of the present application. Figure 5 As shown, the method includes:

[0076] 501. While the jacking wheel of the jacking drive device is gradually raising the wheel, the blocking signal state of the optical detection unit, the tread pressure change parameter output by the pressure sensing unit, and the vertical displacement parameter generated by the displacement measurement unit are obtained to establish a spatial mapping relationship between the expansion path of the pressure decreasing area and the distribution characteristics of the displacement abnormality point.

[0077] Optionally, step 501 may specifically include the following steps:

[0078] 5011. Calculate the change rate of the blocking release rate corresponding to the optical detection channel according to the blocking signal state of the optical detection unit, and extract peak coordinate information corresponding to the change rate.

[0079] Among them, step 5011 may specifically include the following processes: dividing the blocking release rate sequence according to the preset time window, calculating the difference in the blocking release rate in each time window, and dividing the difference by the time window length to obtain a change rate sequence; traversing the change rate sequence, identifying the local maximum point whose rate value is greater than the rate value of the adjacent previous and next time windows, recording its corresponding timestamp and the associated optical detection channel position number to form peak coordinate information.

[0080] 5012. Extract the expansion direction and decreasing gradient of the pressure decreasing area in the tread pressure change parameter output by the pressure sensing unit to determine the pressure decreasing starting point and the pressure decreasing propagation path.

[0081] Among them, step 5012 may specifically include the following processes: dividing the wheel tread into grid units, and counting the decrease amplitude of the pressure change parameter in each grid unit; taking the grid unit with the largest decrease amplitude as the starting point of pressure decrease, and starting from the pressure decrease starting point, tracing the path along the direction of increasing pressure decrease amplitude of adjacent grid units until a pressure increase or stable area is detected, thereby forming a pressure decrease propagation path; calculating the decrease gradient of the pressure decrease propagation path according to the ratio of the pressure decrease amplitude of each grid unit on the pressure decrease propagation path to the path length.

[0082] 5013. Identify the spatial distribution of displacement anomalies in the vertical displacement parameters generated by the displacement measurement unit.

[0083] Among them, step 5013 may specifically include the following processes: continuously sampling the vertical displacement parameters generated by the displacement measurement unit, detecting the displacement increment difference between adjacent sampling points, and if the displacement increment difference exceeds the set mutation threshold, marking the time period between the adjacent sampling points as a nonlinear change segment; recording the starting timestamps of all nonlinear change segments, and calculating the maximum time difference between the starting timestamps detected by different displacement measurement units as the timing deviation; grouping the nonlinear change segments according to the timing deviation, screening out nonlinear change segment groups with time differences less than the synchronization threshold, and in each nonlinear change segment group, screening out unidirectional sudden increase displacement points according to the directional consistency of the displacement increment, marking them as displacement anomaly points and recording the corresponding position coordinates of the displacement anomaly points; and determining the spatial distribution of the displacement anomaly points according to the position coordinates corresponding to multiple displacement anomaly points.

[0084] 5014. Based on the peak coordinate information, the pressure decrease starting point and the pressure decrease propagation path, and the spatial distribution of the displacement abnormality points, a spatial mapping relationship between the pressure decrease area expansion path and the displacement abnormality point distribution characteristics is established.

[0085] Among them, step 5014 may specifically include the following processes: matching the time point in the peak coordinate information with the appearance time of the pressure decrease starting point, if the time difference between the two is less than the set tolerance, marking the pressure decrease starting point as a valid trigger point; taking the valid trigger point as the starting point, according to the extension direction of the pressure decrease propagation path, delineating multiple directional association areas in the wheel-rail contact area, and statistically analyzing the spatial distribution of displacement anomaly points in each directional association area; proportionally allocating the spatial distribution of the displacement anomaly points to the pressure decrease gradient of the corresponding directional association area, if the ratio of density to gradient in any directional association area exceeds a dynamic threshold, determining that the directional association area is a spatial mapping area of the pressure decrease expansion path and the displacement anomaly point; and using the coverage and connection relationship of all spatial mapping areas as the spatial mapping relationship between the pressure decrease area expansion path and the distribution characteristics of the displacement anomaly points.

[0086] In the above scheme, the blocking signal state refers to a binary signal set indicating whether the optical path is blocked or cleared by the wheel. The tread pressure variation parameter is a dynamic numerical sequence of wheel-rail contact pressure changes with wheel lift height. The vertical displacement parameter is a physical quantity that quantifies the wheel lift height. The pressure reduction region expansion path describes the propagation direction and range of pressure dissipation at the wheel-rail contact surface. The displacement anomaly distribution characteristic refers to the spatial locations of sudden displacement increases or fluctuations during wheel lift. The spatial mapping relationship is a correlation matching model for multidimensional data at the wheel-rail contact surface.

[0087] In an embodiment of the present application, first, the blocking signal status of the optical detection unit is collected in real time through step 5011, the number of channels whose blocking is released is counted according to a preset time window (for example, every 0.1 second), and the proportion of the number of blocked channels in each window to the total number of channels is calculated; then the difference in blocking release rates between adjacent time windows is calculated, and the difference is divided by the length of the time window to generate a blocking release rate change rate sequence, which is used to characterize the dynamic intensity of the light path unblocking; then the change rate sequence is traversed to identify the local maximum point, that is, the rate value of a certain time window must be greater than the rate value of the previous window and the next window at the same time, so as to eliminate noise interference; finally, the timestamp corresponding to the local maximum point and the associated optical detection channel position number are recorded to form peak coordinate information, for example, the peak coordinate information includes the timestamp 5.2 seconds and the optical detection channel position numbers 3 to 8, which are used to mark key event nodes in the separation process, such as the light path rapid release stage.

[0088] Subsequently, step 5012 receives the tread pressure parameters output by the pressure sensing unit, divides the wheel-rail contact surface into grid cells, such as a 10 mm by 10 mm square grid, and counts the pressure drop in each grid cell, i.e., the difference between the initial pressure and the current pressure. Then, the grid cell with the largest drop is selected as the starting point of pressure decrease to represent the separation starting position. Starting from this starting point, the path is tracked along the direction of increasing pressure drop of adjacent grid cells, such as when the pressure drop of the right cell is greater than that of the current cell, until it is detected that the pressure has stabilized, such as when the pressure returns to 80% of the initial value or the fluctuation is less than 5%. The expansion direction of the path, such as from the center of the wheel rim to the outside, and the gradient are recorded. The gradient is calculated by dividing the total pressure drop of all grid cells on the path by the path length. For example, a total drop of 50 MPa divided by a path length of 25 mm yields a gradient of 2 MPa per millimeter. Finally, the complete path is determined to be a pressure decrease propagation path, which is used to characterize the dynamic characteristics of pressure dissipation on the wheel-rail contact surface.

[0089] At the same time, step 5013 acquires the vertical displacement parameters of the displacement measurement unit, calculates the incremental displacement difference between adjacent sampling points, and marks the point as a displacement outlier if the difference exceeds a preset mutation threshold (e.g., 0.5 mm / s). The lateral position coordinates of all outlier points are then tallied to form a spatial distribution map of the displacement outliers. Specifically, the vertical displacement parameters generated by the displacement measurement unit are continuously sampled, for example, 1000 times per second, and the incremental displacement difference between adjacent sampling points is calculated (e.g., the displacement value of the subsequent sampling point minus the displacement value of the previous sampling point). If the difference exceeds a preset mutation threshold, for example, 0.5 mm / s, the time period between the adjacent sampling points is marked as a nonlinear change segment, indicating a sudden increase or jitter in displacement. The start timestamps of all nonlinear change segments are recorded, and the maximum time difference between the start timestamps detected by different displacement measurement units, such as the left and right sensors, is calculated as the timing deviation. For example, the left sensor detects the mutation 0.05 seconds later than the right sensor. Nonlinear change segments are grouped according to the timing deviation; for example, segments with a time difference of less than 0.1 seconds are grouped together, thus selecting segments with high synchronization. Within each segment group, the directional consistency of displacement increments is analyzed. For example, if all increments are positive, points with sudden unidirectional increases are identified and marked as abnormal displacement points. Their corresponding lateral track coordinates are recorded, for example, X = 120 mm, Y = 40 mm. Finally, a spatial distribution map is generated based on the coordinates of all abnormal points, reflecting areas of uneven separation.

[0090] Finally, step 5014 is used to align the time point (e.g., 5.2 seconds) in the peak coordinate information generated in step 5011 with the time of the pressure decrease starting point (e.g., 5.1 seconds) determined in step 5012. If the time difference between the two is less than the set tolerance, e.g., 50 milliseconds, the pressure decrease starting point is marked as a valid trigger point to ensure the spatiotemporal consistency between the optical path release and the pressure drop. Taking the valid trigger point as the starting point, according to the extension direction of the pressure decrease propagation path, e.g., extending from the center of the wheel rim to the outside, multiple directional associated areas are delineated on the wheel-rail contact surface, e.g., a sector-shaped area is divided every 30 degrees along the path direction. The displacement abnormal points in step 5013 are counted in each direction. The density within the direction-related area, for example, the number of outliers per square centimeter, is proportionally distributed to the pressure decrease gradient of the corresponding area (for example, 2 MPa per millimeter) to calculate the density / pressure decrease gradient ratio. If the ratio in a certain area exceeds a dynamic threshold, the area is determined to be a spatial mapping area of the pressure decrease expansion path and displacement anomalies, indicating that the pressure dissipation here is strongly correlated with the displacement mutation. The dynamic threshold can be set as needed, for example, to 0.8. Finally, the coverage and connection relationship of all spatial mapping areas are integrated to generate the overlapping trajectory of the pressure decrease area expansion path and the distribution characteristics of the displacement anomalies on the wheel-rail contact surface, forming a complete spatial mapping relationship.

[0091] Specifically, when integrating spatial mapping areas, the team first identifies valid mapping areas based on the density-to-pressure gradient ratio within the directional correlation region. For example, the left wheel rim sector region with a density / gradient ratio of 1.2 greater than the dynamic threshold (0.8) is marked as a valid mapping area. The spatial connectivity between mapping areas is then analyzed based on the direction of the pressure reduction propagation path. For example, if the left wheel rim sector region and the central region have a continuous path, adjacent or continuous mapping areas are merged into extended subpaths. Finally, based on the coverage and topological connectivity of all subpaths, overlapping trajectories of the pressure reduction extension path and the distribution of displacement anomalies on the wheel-rail contact surface are generated. For example, a fan-shaped trajectory radiating outward from the center of the wheel rim represents a complete spatial mapping relationship, representing areas with a strong correlation between pressure dissipation and displacement mutations.

[0092] In actual application, in the wheel detection scenario with a wheel diameter of 860 mm, the jacking drive device's jacking wheel is started and the wheel is lifted step by step. The specific process is as follows: the optical detection unit monitors the light path blocking status in real time. When it is lifted to the 5th second, it is detected that the blocking release rate change rate of channels 3 to 8 reaches a peak, and the timestamp at this time is recorded as 5.2 seconds and the corresponding channel position; the pressure sensing unit synchronously collects the wheel-rail contact surface pressure data and finds that the pressure in the center area of the rim continuously drops from 12 MPa to 4 MPa, and the pressure drop diffuses along the outer direction of the wheel. The gradient is calculated to be 2 MPa per millimeter, thereby determining that the starting point of the pressure decrease is the rim center coordinate (X=120 mm, Y=0); at the same time, the displacement measurement unit detects that when the wheel is lifted to 5 mm, the displacement of the left rim area suddenly increases by 0.8 mm, which is marked as a displacement abnormality point and its position coordinates are recorded (X=80 mm, Y=-40 mm). The processing unit time-aligns the peak time of optical detection (5.2 seconds) with the starting time of pressure decrease (5.1 seconds). The time difference between the two, 0.1 seconds, is less than the set tolerance threshold of 0.2 seconds, and is determined to be a valid correlation event. Subsequently, a fan-shaped detection area is delineated along the direction of pressure propagation (extending outward), and the density of displacement anomaly points in the left wheel rim area is counted as 5 points per square centimeter. Combined with the pressure gradient of 2 MPa per millimeter in this area, the density-to-gradient ratio is calculated to be 2.5 (5 / 2). After exceeding the dynamic threshold of 0.8, the area is determined to be a strong correlation mapping area between pressure dissipation and displacement mutation. Finally, the spatial position and path continuity of all mapping areas are integrated to generate overlapping trajectories extending from the center of the wheel rim to the left outer side, forming a complete spatial mapping relationship, which intuitively characterizes the dynamic correlation between the pressure dissipation path and the displacement anomaly distribution during wheel-rail separation.

[0093] The overall solution of step 501 above realizes refined modeling of the wheel-rail separation process through spatiotemporal correlation and dynamic matching of multi-source data. The optical signal accurately captures the separation trigger node, the pressure data reveals the contact force dissipation law, and the displacement anomaly points locate the uneven separation area. The spatial mapping relationship finally constructed intuitively reflects the physical propagation characteristics of the separation state, providing a high-confidence data basis for subsequent judgment, avoiding the risk of misjudgment by a single sensor, and significantly improving detection accuracy and reliability.

[0094] 502. Map the blocking signal state to a blocking release rate of an optical detection channel, and calculate the cumulative displacement value when the wheel tread is separated based on the spatial mapping relationship and the blocking release rate of the optical detection channel.

[0095] Optionally, step 502 includes:

[0096] 5021. Count the duration of the blocking signal of each optical detection channel during the lifting process, and calculate the blocking release weight factor of each optical detection channel according to the blocking signal duration.

[0097] 5022. Convert the ratio of the number of optical detection channels where the blocking signals disappear to the total number of optical detection channels into a blocking release rate sequence according to the lifting time sequence.

[0098] 5023. Filtering out the wheel tread area that coincides with the distribution area of the abnormal displacement points according to the pressure decreasing expansion path marked in the spatial mapping relationship;

[0099] 5024. Accumulate the vertical displacement increments detected by all displacement measurement units in the wheel tread area during the lifting phase, and perform weighted correction on each vertical displacement increment according to the blocking release rate sequence and the corresponding blocking release weight factor to generate a displacement accumulation value.

[0100] In the above scheme, the blocking signal status refers to the real-time signal set of the light path being blocked or released by the wheel, and the blocking release rate is the ratio sequence of the number of channels where the blocking signal disappears to the total number of channels. The blocking signal duration is the length of time that the light path of a single channel is continuously blocked during the lifting process. The blocking release weight factor is calculated based on the blocking signal duration and is used to characterize the reliability weight of the channel unblocking. The cumulative displacement value is the sum of the displacements corrected by the blocking release rate sequence and the weight factor after adding the vertical displacement increments in the wheel tread area, reflecting the actual lifting amount of the wheel-rail separation process. The pressure reduction expansion path marked by the spatial mapping relationship is the propagation direction and range of the pressure dissipation on the wheel-rail contact surface, and the displacement anomaly point distribution area is the set of spatial positions of sudden increases or jitters in displacement.

[0101] In an embodiment of the present application, step 5021 is used to traverse the blocking signal status of each optical detection channel, and the duration of the light path being blocked during the lifting process is counted. For example, channel A is blocked for 5 seconds, and the weight factor is calculated based on the duration. The formula is weight factor = 1 / (1 + duration), which represents the credibility of the channel being unblocked.

[0102] Secondly, in step 5022, the lifting process is divided into fixed time windows according to the lifting time sequence, for example, each 0.1 second is a node. The number of optical detection channels in each window where the blocking signal disappears is counted in real time, and its proportion to the total number of channels is calculated. For example, if the total number of channels is 20, if 15 channels are unblocked in a window, the proportion is 15 / 20 = 75%. The proportion values of each window are recorded in sequence according to the lifting time sequence (such as 0 seconds, 0.1 seconds, 0.2 seconds...) to generate a blocking release rate sequence. For example, if the lifting process lasts for 1 second, a sequence is generated at 0.1 second intervals: the release rate at 0.1 second is 50% (10 / 20), at 0.2 second is 75% (15 / 20), at 0.3 second is 90% (18 / 20), and so on to form a release rate sequence that increases over time, which is used to characterize the dynamic trend of the separation process.

[0103] Next, the generated spatial mapping relationship is obtained through step 5023, and the pressure reduction expansion path is extracted, such as the fan-shaped path extending outward from the rim center coordinate X = 120 mm, Y = 0. At the same time, the displacement abnormality distribution area is obtained, such as the displacement sudden increase point in the left rim area from X = 80 to 160 mm, Y = -40 to 0. Through spatial superposition analysis, the overlapping area of the two is screened, such as the outer side of the left rim from X = 100 to 140 mm, Y = -20 to 0, and marked as a valid separation area to ensure that subsequent displacement accumulation values only accumulate vertical displacement data in this area. For example, if the pressure path covers the rim center to the outer side and the displacement abnormalities are concentrated on the outer side of the left rim, the overlapping area is the fan-shaped area where the two overlap, and subsequent calculations are only performed on this area.

[0104] Finally, the vertical displacement increments detected by all displacement measurement units in the overlapping area during the lifting phase are accumulated, for example, 0.2 mm each time. According to the blocking release rate sequence, for example, the release rate at a certain moment is 80% and the corresponding weight factor, for example, the channel weight factor is 0.8, the displacement increment is weightedly corrected, for example, increment × release rate × weight factor, and finally the displacement cumulative value is generated.

[0105] In practical applications, for example, taking a wheel with an 840mm diameter as an example, after the lifting drive is activated, the optical detection unit detects the disappearance of blocking signals in 15 channels during the lifting process. The duration of the blocking signal for each channel is counted, and a weighting factor is calculated. For example, channel 3 has a duration of 2 seconds and a weighting factor of 0.33. A sequence of blocking release rates is generated based on the lifting time sequence, for example, the release rate in the third second is 70%. Based on the spatial mapping relationship, the processing unit selects the area on the outer side of the left wheel rim where the pressure reduction expansion path coincides with the displacement anomaly point. The displacement increments detected by the displacement measurement unit within this area are accumulated, for example, for each 0.3mm lift. Combined with the current blocking release rate of 70% and the weighting factor of 0.33, a weighted displacement increment of 0.3 × 0.7 × 0.33 ≈ 0.07mm is calculated and added to the total displacement accumulation value. Finally, when the accumulated value continuously increases and the blocking release rate meets the standard, wheel-rail separation is determined.

[0106] In the complete solution for step 502, the reliability weight of the optical blocking signal, the dynamic release rate sequence, and the spatial mapping relationship are integrated to achieve precise correction of the cumulative displacement value. The blocking release weight factor reduces the weight of transient interference signals, the blocking release rate sequence reflects the dynamic separation trend, and the spatial mapping relationship ensures that the displacement calculation focuses on the effective area. The resulting cumulative displacement value eliminates noise interference and reflects the actual lift during the separation process, providing a highly reliable quantitative basis for wheel-rail separation determination and significantly improving the stability and accuracy of the detection results.

[0107] 503. When the accumulated displacement value shows a unidirectional increasing characteristic during the continuous lifting stage, and the blocking release rate of the optical detection channel is greater than a preset threshold, the wheel-rail separation is determined, and a control instruction is generated to control the lifting drive device to terminate the operation.

[0108] Optionally, step 503 includes:

[0109] 5031. Record the cumulative displacement value in the order of the lifting stages. If the cumulative displacement value of the current stage is greater than that of the previous stage and the difference between the cumulative displacement values continues to increase, it is marked as unidirectional increasing.

[0110] 5032. Count the proportion of the optical detection channels whose blocking release rate is greater than a preset threshold. If the proportion of the number of channels exceeds the preset threshold in a consecutive number of lifting stages, it is marked as meeting the effective ratio standard.

[0111] 5033. When the one-way increasing mark and the effective ratio reaching mark exist at the same time, a control instruction is generated to control the lifting drive device to terminate the operation.

[0112] In the above scheme, the cumulative displacement value is the sum of the vertical displacements accumulated and corrected during the wheel tread separation process. The unidirectional increasing characteristic means that the cumulative displacement value continues to increase during the consecutive lifting stages, and the incremental difference gradually expands. The blocking release rate is the ratio sequence of the number of optical detection channels where the blocking signal disappears to the total number of channels, and the preset threshold is the set minimum blocking release rate standard. The effective proportion standard means that the proportion of the number of channels with a blocking release rate greater than the preset threshold remains stable over multiple consecutive lifting stages. The control command is the control signal that triggers the jacking drive device to stop.

[0113] In an embodiment of the present application, first, the cumulative displacement value is recorded in the order of the lifting stages. For example, each stage is when the lifting mechanism rises by 1 mm. If the cumulative displacement value of the current stage is greater than that of the previous stage and the difference between the current stage and the previous stage is greater than the difference between the previous stage and the earlier stage, it is marked as a one-way increase, indicating that there is no regression in the lifting process and the separation trend is stable.

[0114] Secondly, the number of channels in the optical detection channel whose blocking release rate is greater than the preset threshold is counted, and their proportion to the total number of channels is calculated. For example, if the preset threshold is 80%, if the proportion of the number of channels in three consecutive stages (such as stages 5, 6, and 7) is ≥80%, it is marked as meeting the effective proportion standard to ensure the continuity of the separation state.

[0115] Finally, when the one-way increasing mark and the effective ratio reaching standard mark exist at the same time, that is, the displacement accumulation value continues to increase and the blocking release rate reaches the standard stably, a control instruction is generated and sent to the lifting drive device to terminate the lifting operation and avoid excessive lifting or incomplete separation.

[0116] For example, taking the inspection of a wheel with a wheel diameter of 860 mm as an example, the lifting drive device lifts the wheel step by step, and the processing unit records the cumulative displacement value of each stage. The cumulative displacement value of stage 3 is 3.2 mm, stage 4 is 4.0 mm, and stage 5 is 5.1 mm. The difference gradually increases and is marked as unidirectional increase. At the same time, the optical detection channel blocking release rate in stages 4 to 6 is 85%, 88%, and 83% respectively. The three consecutive stages exceeded the preset threshold of 80%, and were marked as effective ratios. After the processing unit detects the coexistence of the two marks, it immediately generates a control command to stop lifting. The wheel is accurately lifted to the completely off-track position, and subsequent flaw detection operations are carried out normally.

[0117] In the complete solution for step 503, the high reliability of wheel-rail separation determination is ensured through dual verification of the unidirectional increase in the accumulated displacement value and the consistent compliance of the blocking release rate. The unidirectional increase eliminates interference from displacement fluctuations, while the blocking release rate threshold verifies the adequacy of the separation range. The synergistic effect of these two prevents premature or late termination of the jacking operation, significantly improving detection accuracy and equipment safety while ensuring the stable execution of subsequent flaw detection processes.

[0118] Optionally, the method further includes:

[0119] 504. In response to the control instruction, the driving rotation unit is started to drive the wheel to rotate, and the acoustic wave detection unit is controlled to perform defect detection operations in accordance with the wheel surface based on the channel activation sequence of the optical detection unit.

[0120] In this step, the control command is the signal that triggers the device to execute subsequent actions. The drive rotation unit drives the wheel through a mechanical transmission device. The acoustic detection unit uses an ultrasonic probe to detect internal wheel defects. The channel activation sequence is a set of optical channel position numbers in the optical detection unit that meet the blockage release rate requirements, which is used to guide the probe movement trajectory. Wheel contact refers to maintaining constant contact pressure between the ultrasonic probe and the wheel surface to ensure signal transmission quality.

[0121] In this embodiment, after determining wheel-rail separation, the processing unit sends control instructions to the drive and rotation unit and the acoustic detection unit. The servo motor of the drive and rotation unit engages the wheel shaft end through a gear, driving the wheel to rotate at a set speed, such as 5 revolutions per minute, to ensure full wheel tread coverage. Simultaneously, the optical channel position numbers of channels 3 to 15 with a satisfactory blockage release rate are extracted from the optical detection unit, and a probe movement priority sequence is generated from high to low according to the release rate. The robotic arm of the acoustic detection unit dynamically adjusts the probe position according to the sequence. For example, in the outer area of the wheel rim corresponding to channel 3, the probe is pressed against the wheel tread with constant pressure and emits an ultrasonic pulse. After the probe receives the reflected acoustic signal, the processing unit analyzes the echo amplitude and delay characteristics to identify internal defects such as cracks or cavities, and generates a defect distribution map in real time. For example, after a wheel with a diameter of 860 mm is lifted completely off the track, the drive and rotation unit rotates the wheel at 5 revolutions per minute. The acoustic detection unit preferentially scans the wheel tread area corresponding to channels 5 to 12 with a blockage release rate of 90%. A 2 mm deep crack on the inner side of the wheel rim is detected and marked, completing full wheel tread defect detection.

[0122] In practical applications, taking the inspection of a wheel with a wheel diameter of 860 mm as an example, the processing unit sends a control command after determining that the wheel-rail is separated, and the drive rotation unit immediately starts and drives the wheel to rotate at a uniform speed of 5 revolutions per minute; the channel activation sequence of the optical detection unit shows that the blocking release rate of channels 5 to 12 is more than 90%, corresponding to the middle to outer areas of the wheel surface; the robotic arm of the acoustic wave detection unit first moves to the wheel surface position corresponding to channel 5 according to the priority, and the probe sticks to the wheel surface and emits ultrasonic pulses, detecting an echo abnormality on the inside of the wheel rim, which is marked as a potential crack with a depth of 2 mm; as the wheel continues to rotate, the probe covers the corresponding areas of channels 6 to 12 in turn, and after completing the full-circle wheel surface inspection, a defect report containing the crack location and size is generated.

[0123] In the aforementioned step 504, the coordinated control of the rotation drive unit and the acoustic detection unit enables automated flaw detection after wheel derailment. The channel activation sequence guides the probe to prioritize areas with high-probability defects, improving detection efficiency. Constant contact pressure ensures stable ultrasonic signal transmission, preventing missed detections. The rotational motion ensures full-circle inspection of the wheel surface. This step seamlessly connects separation determination with defect detection, forming a complete maintenance operation closed loop, significantly improving detection accuracy and the level of automation.

[0124] The following is a complete embodiment of steps 501 to 504:

[0125] During the online ultrasonic flaw detection of a certain type of rail vehicle wheel with a diameter of 860 mm, after the jacking drive device's jacking wheel is started, the pressure sensing unit detects the pressure changes on the wheel-rail contact surface in real time. The initial pressure is 12 MPa. During the lifting process, the pressure decreases from the center of the wheel rim to the outside to 3 MPa.

[0126] The optical detection unit synchronously monitors the light path blocking status. When the wheel contacts the track, 15 of the 20 light paths are blocked. When the wheel is lifted to 4 mm, the number of blocked channels increases to 18.

[0127] The displacement measurement unit records the vertical displacement parameters, and when the cumulative lift is 5 mm, a sudden increase of 0.5 mm displacement of the left wheel rim is detected. The processing unit integrates the pressure reduction path, the distribution of displacement anomaly points and the peak value of the blocking release rate, among which the blocking release rate at the 5th second reaches 90%, constructs a spatial mapping relationship and locates the separation core area. Then, the blocking duration of each optical channel is counted and the weight factor is calculated. For example, channel 3 lasts for 3 seconds, and the weight factor is 1 / (1+3)=0.25. Combined with the blocking release rate sequence of 70% at the 3rd second, 85% at the 4th second, and 90% at the 5th second, the displacement increment is weighted and corrected. The displacement increment of 0.5 mm in the left wheel rim area is corrected to 0.5×0.9×0.25≈0.11 mm, which is added to the total displacement cumulative value.

[0128] When the cumulative displacement value increases unidirectionally from stage 3 to stage 5, from 4.0 mm to 4.5 mm and then to 5.1 mm, and the blocking release rate meets the standard for three consecutive stages, a control command is generated to terminate the jacking, and the wheel is lifted to 5.1 mm and completely off the track. The rotation unit is then driven to rotate the wheel at a constant speed of 5 revolutions per minute. Based on the activation sequence of channels 5 to 18 that meet the blocking release rate standards, the acoustic wave detection unit prioritizes the outer area of the wheel rim. The probe emits ultrasonic waves and identifies an internal crack with a depth of 2 mm, completing non-destructive testing of the entire wheel surface.

[0129] This application uses dynamic fusion of multi-source sensor data and real-time feedback control to achieve accurate determination of wheel-rail separation and adaptive lifting. The accumulated displacement value, after deformation compensation and weight correction, truly reflects the effective lift amount. A dual verification mechanism ensures high reliability of separation determination. During the flaw detection phase, optical channel priority coverage and rotational coordinated control are used to improve the efficiency and comprehensiveness of defect detection, forming a fully closed-loop process of separation detection, dynamic control, and defect identification. This significantly addresses the wheel diameter adaptability defects of traditional fixed lifting strategies, while balancing detection accuracy, equipment safety, and maintenance automation.

[0130] Optionally, the method also includes: synchronously collecting the contact surface image of the wheel and the rail during the lifting process, extracting the illumination reflection characteristics and contour deformation parameters of the contact area from the contact surface image; performing a difference comparison between the illumination reflection characteristics and a preset standard reflection template in the wheel-rail fitting state to generate a deformation compensation factor; dynamically correcting the accumulated displacement value based on the deformation compensation factor, and integrating the contour deformation parameters to optimize the boundary accuracy of the spatial mapping relationship.

[0131] In this step, the contact surface image is real-time image data of the wheel-rail contact area. The illumination reflection feature refers to the light intensity distribution pattern in the image caused by surface material or deformation. The profile deformation parameter is the geometric distortion of the wheel contact surface edge. The standard reflection template is a pre-stored reference image of the reflection feature when the wheel and rail are in full contact. The deformation compensation factor is a correction coefficient generated by comparing the real-time reflection feature with the template. It is used to eliminate deformation interference on displacement detection.

[0132] In an embodiment of the present application, during the lifting process, a high-resolution industrial camera is used to synchronously capture images of the contact surface between the wheel and the rail, and the image is pre-processed by grayscale, denoising, and edge enhancement. Light reflection features such as the distribution of highlight areas and the reflection intensity gradient are extracted, and contour deformation parameters such as the local curvature of the rim edge are calculated; the real-time light reflection features are compared with the pre-stored standard reflection template at the pixel level to generate a difference matrix, and a deformation compensation factor is generated based on the amplitude distribution of the difference matrix. The greater the difference in the area, the higher the weight of the compensation factor. For example, a difference value of 0.8 corresponds to a compensation factor of 0.6.

[0133] The accumulated displacement value is weightedly corrected based on the compensation factor. For example, the displacement increment of the deformation area of 0.3 mm is multiplied by the compensation factor of 0.6 to be corrected to 0.18 mm.

[0134] Finally, the system integrates contour deformation parameters, such as a 2-degree curvature of the left rim, to adjust the boundary accuracy of the pressure reduction path and displacement anomalies in the spatial mapping relationship. For example, the boundary of the left rim mapping area is retracted by 5 mm. For example, in a wheel inspection, the contact surface image shows abnormal highlight reflections and a curved edge on the left rim. A compensation factor of 0.6 is generated to correct the inflated displacement in this area. Simultaneously, the mapping boundary is optimized to avoid misjudgment of non-contact areas, ultimately improving detection accuracy.

[0135] In practical applications, taking a wheel inspection as an example, an industrial camera captures an image of the contact surface during the lifting process. The image shows a high-gloss reflective area on the left side of the wheel rim, with a slightly curved edge profile. The processing unit extracts the illumination reflection characteristics of this area and compares them pixel-by-pixel with a pre-stored standard reflection template to generate a difference matrix. The difference value for the left region is 0.8, and the corresponding compensation factor is set to 0.6. The 0.3 mm increment in the cumulative displacement from this region is corrected to 0.3 × 0.6 = 0.18 mm. Simultaneously, the contour deformation parameters detect a 2-degree curvature on the left side of the wheel rim. Based on this, the spatial mapping relationship retracts the left mapping area boundary by 5 mm to avoid misjudging non-contact areas. Through deformation compensation and boundary optimization, the system accurately corrects for displacement artifacts and improves detection boundary accuracy, ensuring the reliability of wheel-rail separation determination.

[0136] In these steps, image feature analysis and deformation compensation mechanisms significantly reduce displacement detection errors caused by wheel surface deformation or foreign matter adhesion. Light reflection difference comparison accurately locates abnormal areas, deformation compensation factors dynamically suppress inflated displacement, and profile parameters optimize spatial mapping boundaries. These three factors work together to improve the detection system's environmental adaptability and boundary determination accuracy, ensuring the reliability of wheel-rail separation detection results under complex operating conditions.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting wheel tread derailment of a railway vehicle, characterized in that: Lifting drive devices are symmetrically arranged on both sides of the longitudinal track. Each lifting drive device includes two jacking wheels, which are used to lift the wheel. A pressure sensing unit is arranged between the two jacking wheels. An optical detection unit is installed on the outer side of the lifting drive device, and its optical path direction is orthogonal to the wheel motion plane. At the same time, a displacement measurement unit is integrated on the jacking wheels. When the jacking wheels lift the wheel, the displacement measurement unit moves synchronously to generate the vertical displacement parameters of the wheel. The pressure sensing unit, the optical detection unit and the displacement measurement unit form a three-dimensional detection coverage area in the wheel-rail contact area. When the wheel contacts the track, the light path of the optical detection unit is completely blocked by the wheel; The method comprises: During the process of the jacking drive device's jacking wheel gradually raising the wheel, a blocking signal state of the optical detection unit, a tread pressure change parameter output by the pressure sensing unit, and a vertical displacement parameter generated by the displacement measurement unit are obtained to establish a spatial mapping relationship between an expansion path of a pressure decreasing region and a distribution characteristic of abnormal displacement points; Mapping the blocking signal state to a blocking release rate of the optical detection channel, and calculating the cumulative displacement value when the wheel tread is separated based on the spatial mapping relationship and the blocking release rate of the optical detection channel; When the accumulated displacement value presents a unidirectional increasing characteristic in the continuous lifting stage and the blocking release rate of the optical detection channel is greater than a preset threshold, the wheel-rail separation is determined, and a control instruction is generated to control the jacking drive device to terminate the operation.

2. The method according to claim 1, characterized in that Also includes: During the lifting process, images of the contact surfaces of the wheel and the rail are synchronously collected, and illumination reflection characteristics and contour deformation parameters of the contact area are extracted from the contact surface images; Comparing the illumination reflection characteristics with a preset standard reflection template in a wheel-rail fitting state to generate a deformation compensation factor; The displacement accumulation value is dynamically corrected based on the deformation compensation factor, and the boundary accuracy of the spatial mapping relationship is optimized by fusing the contour deformation parameter.

3. The method according to claim 1, characterized in that Acquiring the blocking signal state of the optical detection unit, the tread pressure change parameter output by the pressure sensing unit, and the vertical displacement parameter generated by the displacement measurement unit to establish a spatial mapping relationship between the pressure decreasing area expansion path and the displacement abnormal point distribution characteristics includes: Calculating the change rate of the blocking release rate corresponding to the optical detection channel according to the blocking signal state of the optical detection unit, and extracting the peak coordinate information corresponding to the change rate; Extracting the expansion direction and decreasing gradient of the pressure decreasing area from the tread pressure change parameter output by the pressure sensing unit to determine the pressure decreasing starting point and the pressure decreasing propagation path; identifying a spatial distribution of displacement anomalies in the vertical displacement parameters generated by the displacement measurement unit; Based on the peak coordinate information, the pressure decrease starting point and pressure decrease propagation path, and the spatial distribution of the displacement abnormal points, a spatial mapping relationship between the pressure decrease area expansion path and the displacement abnormal point distribution characteristics is established.

4. The method according to claim 3, characterized in that The establishing of a spatial mapping relationship between the pressure decrease region expansion path and the distribution characteristics of the displacement abnormal points based on the peak coordinate information, the pressure decrease starting point, the pressure decrease propagation path, and the spatial distribution of the displacement abnormal points includes: Matching the time point in the peak coordinate information with the occurrence time of the pressure decrease starting point, and if the time difference between the two is less than a set tolerance, marking the pressure decrease starting point as a valid trigger point; Taking the effective trigger point as the starting point, multiple directional associated areas are delineated in the wheel-rail contact area according to the extension direction of the pressure decrease propagation path, and the spatial distribution of displacement abnormal points in each directional associated area is counted; Proportionally distribute the spatial distribution of the displacement anomaly points and the pressure decrease gradient of the corresponding directional association area. If the ratio of density to gradient in any directional association area exceeds a dynamic threshold, the directional association area is determined to be the spatial mapping area of the pressure decrease expansion path and the displacement anomaly points. The coverage and connection relationship of all spatial mapping areas are used as the spatial mapping relationship between the expansion path of the pressure reduction area and the distribution characteristics of the displacement anomaly points.

5. The method according to claim 1, characterized in that Mapping the blocking signal state to a blocking release rate of the optical detection channel, and calculating the cumulative displacement value when the wheel tread is separated according to the spatial mapping relationship and the blocking release rate of the optical detection channel, includes: Counting the duration of the blocking signal of each optical detection channel during the lifting process, and calculating the blocking release weight factor of each optical detection channel according to the blocking signal duration; The ratio of the number of optical detection channels where the blocking signals disappear to the total number of optical detection channels is converted into a blocking release rate sequence according to the lifting time sequence; Screening out a wheel tread area that coincides with a distribution area of abnormal displacement points according to a pressure decreasing expansion path marked in the spatial mapping relationship; The vertical displacement increments detected by all displacement measurement units in the wheel tread area during the lifting phase are accumulated, and each vertical displacement increment is weightedly corrected according to the blocking release rate sequence and the corresponding blocking release weight factor to generate a displacement accumulation value.

6. The method according to claim 3, characterized in that The calculating the change rate of the blocking release rate corresponding to the optical detection channel according to the blocking signal state of the optical detection unit, and extracting the peak coordinate information corresponding to the change rate, includes: Divide the blocking release rate sequence by the preset time window, calculate the difference of the blocking release rate in each time window, and divide the difference by the time window duration to obtain the change rate sequence; The change rate sequence is traversed to identify the local maximum point whose rate value is greater than the rate value of the adjacent time windows, and the corresponding timestamp and the associated optical detection channel position number are recorded to form peak coordinate information.

7. The method according to claim 3, characterized in that Extracting the expansion direction and decreasing gradient of the pressure decreasing area in the tread pressure change parameter output by the pressure sensing unit to determine the pressure decreasing starting point and the pressure decreasing propagation path includes: The wheel tread is divided into grid units, and the decrease amplitude of the pressure change parameter in each grid unit is counted; The grid cell with the largest pressure drop is taken as the starting point of pressure drop, and starting from the pressure drop starting point, the path is traced along the direction of increasing pressure drop of adjacent grid cells until a pressure increase or stable area is detected, thereby forming a pressure drop propagation path; The decreasing gradient of the pressure decreasing propagation path is calculated according to the ratio of the pressure drop amplitude of each grid unit on the pressure decreasing propagation path to the path length.

8. The method according to claim 3, characterized in that The identifying the spatial distribution of abnormal displacement points in the vertical displacement parameters generated by the displacement measurement unit includes: Continuously sampling the vertical displacement parameter generated by the displacement measurement unit, detecting the displacement increment difference between adjacent sampling points, and marking the time period between the adjacent sampling points as a nonlinear change section if the displacement increment difference exceeds a set mutation threshold; Record the starting timestamps of all nonlinear change segments and calculate the maximum time difference between the starting timestamps detected by different displacement measurement units as the timing deviation; The nonlinear change segments are grouped according to the timing deviation, and nonlinear change segment groups whose time differences are less than the synchronization threshold are screened out. In each nonlinear change segment group, displacement points with unidirectional sudden increases are screened out based on the directional consistency of the displacement increments. These points are marked as displacement anomalies and the position coordinates corresponding to the displacement anomalies are recorded. The spatial distribution of the displacement anomaly points is determined according to the position coordinates corresponding to the multiple displacement anomaly points.

9. The method according to claim 1, characterized in that When the accumulated displacement value presents a unidirectional increasing characteristic during the continuous lifting stage and the blocking release rate of the optical detection channel is greater than a preset threshold, it is determined that the wheel-rail is separated, and a control instruction is generated to control the lifting drive device to terminate the operation, including: Record the cumulative displacement values in the order of the lifting stages. If the cumulative displacement value of the current stage is greater than that of the previous stage and the difference between the cumulative displacement values continues to increase, it is marked as unidirectional increase; Counting the proportion of channels in the optical detection channels whose blocking release rate is greater than a preset threshold, if the proportion of the number of channels exceeds the preset threshold in a consecutive number of lifting stages, it is marked as meeting the effective ratio standard; When the one-way increasing mark and the effective ratio reaching mark exist at the same time, a control instruction is generated to control the lifting drive device to terminate the operation; The method further comprises: In response to the control instruction, the driving rotation unit is started to drive the wheel to rotate, and the acoustic wave detection unit is regulated to perform defect detection operations in accordance with the wheel surface based on the channel activation sequence of the optical detection unit.

10. A wheel tread derailment detection system for a railway vehicle, characterized in that: It includes a lifting drive device, an optical measurement unit and a processing unit; wherein each lifting drive device includes two lifting wheels, a pressure sensing unit and a displacement detection unit, and the lifting drive device is arranged on both sides of the track in the longitudinal direction, and each lifting drive device includes two lifting wheels, and the lifting wheels are used to lift the wheels; A pressure sensing unit is provided between the two top rotating wheels, and the pressure sensing unit is used to output tread pressure change parameters; An optical detection unit is installed on the outer side of the jacking drive device, and its light path direction is orthogonal to the wheel movement plane. When the wheel contacts the track, the light path of the optical detection unit is completely blocked by the wheel; The top runner is integrated with a displacement measuring unit. When the top runner lifts the wheel, the displacement measuring unit moves synchronously to generate the vertical displacement parameters of the wheel. The pressure sensing unit, the optical detection unit and the displacement measuring unit form a three-dimensional detection coverage area in the wheel-rail contact area. The processing unit is used to obtain the blocking signal state of the optical detection unit, the tread pressure change parameter output by the pressure sensing unit, and the vertical displacement parameter generated by the displacement measurement unit during the process of the jacking drive device raising the wheel step by step, so as to establish a spatial mapping relationship between the pressure decrease area expansion path and the displacement abnormality point distribution characteristics; map the blocking signal state to the blocking release rate of the optical detection channel, and calculate the displacement accumulation value when the wheel tread is separated according to the spatial mapping relationship and the blocking release rate of the optical detection channel; when the displacement accumulation value presents a unidirectional increasing characteristic in the continuous lifting stage and the blocking release rate of the optical detection channel is greater than a preset threshold, it is determined that the wheel and rail are separated, and a control instruction is generated to control the jacking drive device to terminate the operation.

Images